Análisis de modelos SOM - Frecuencia datos de entrada: mes

Modelo

• ID: 314
• Descripción:
• Frecuencia: mes
• Variables: precip, longitud, latitud, altitud
• Dimensiones del mapa: 5,5
• Iteraciones: 10000
• Parámetros adicionales:

source("../../lib/som-utils.R")

Attaching package: 'dplyr'

The following objects are masked from 'package:stats':

    filter, lag

The following objects are masked from 'package:base':

    intersect, setdiff, setequal, union

source("../../lib/maps-utils.R")

Linking to GEOS 3.8.0, GDAL 3.0.4, PROJ 6.3.1

Carga del modelo desde disco

mpr.set_base_path_analysis()
model <- mpr.load_model("som-314.rds.xz")
summary(model)

SOM of size 5x5 with a hexagonal topology and a bubble neighbourhood function.
The number of data layers is 1.
Distance measure(s) used: sumofsquares.
Training data included: 94881 objects.
Mean distance to the closest unit in the map: 0.346.

plot(model, type="changes")

Carga del dataset de entrada

df <- mpr.load_data("datos_mes.csv.xz")

df

summary(df)

 id_estacion           fecha             fecha_cnt           tmax      
 Length:94881       Length:94881       Min.   : 1.000   Min.   :-53.0  
 Class :character   Class :character   1st Qu.: 4.000   1st Qu.:148.0  
 Mode  :character   Mode  :character   Median : 6.000   Median :198.0  
                                       Mean   : 6.497   Mean   :200.2  
                                       3rd Qu.: 9.000   3rd Qu.:255.0  
                                       Max.   :12.000   Max.   :403.0  
      tmin             precip           nevada           prof_nieve      
 Min.   :-121.00   Min.   :  0.00   Min.   :0.000000   Min.   :   0.000  
 1st Qu.:  53.00   1st Qu.:  3.00   1st Qu.:0.000000   1st Qu.:   0.000  
 Median :  98.00   Median : 10.00   Median :0.000000   Median :   0.000  
 Mean   :  98.86   Mean   : 16.25   Mean   :0.000295   Mean   :   0.467  
 3rd Qu.: 148.00   3rd Qu.: 22.00   3rd Qu.:0.000000   3rd Qu.:   0.000  
 Max.   : 254.00   Max.   :422.00   Max.   :6.000000   Max.   :1834.000  
    longitud        latitud            altitud      
 Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:38.28   1st Qu.: -5.6417   1st Qu.:  42.0  
 Median :40.82   Median : -3.4500   Median : 247.0  
 Mean   :39.66   Mean   : -3.4350   Mean   : 418.5  
 3rd Qu.:42.08   3rd Qu.:  0.4914   3rd Qu.: 656.0  
 Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

Carga de los mapas

world <- ne_countries(scale = "medium", returnclass = "sf")
spain <- subset(world, admin == "Spain")

Mapa de densidad

plot(model, type="count", shape = "straight", palette.name = mpr.degrade.bleu)

Número de elementos en cada celda:

nb <- table(model$unit.classif)
print(nb)

   1    2    3    4    5    6    7    8    9   10   11   12   13   14   15   16 
 784 2957 3702 6668 2010  125  863 1549 5148 1779  949 3144 7133 3081 4251 1189 
  17   18   19   20   21   22   23   24   25 
3113 3897 5326 4743 5652 8385 8379 8106 1948 

Comprobación de nodos vacíos:

dim_model <- 5*5;
len_nb = length(nb);
empty_nodes <- dim_model != len_nb;
if (empty_nodes) {
  print(paste("[Warning] Existen nodos vacíos: ", len_nb, "/", dim_model))
}

Mapa de distancia entre vecinos

plot(model, type="dist.neighbours", shape = "straight")

Influencia de las variables

model_colnames = c("precip", "longitud", "latitud", "altitud")
model_ncol = length(model_colnames)

Mapa de variables.

plot(model, shape = "straight")

Mapa de calor por variable

par(mfrow=c(3,4))
for (j in 1:model_ncol) {
  plot(model, type="property", property=getCodes(model,1)[,j],
    palette.name=mpr.coolBlueHotRed,
    main=model_colnames[j],
    cex=0.5, shape = "straight")
}

Correlación para cada columna del vector de nodos

if (!empty_nodes) {
  cor <- apply(getCodes(model,1), 2, mpr.weighted.correlation, w=nb, som=model)
  print(cor)
}

          precip   longitud      latitud    altitud
[1,] -0.05792794  0.6915453  0.719734312  0.1186730
[2,] -0.25427824 -0.4878560 -0.006193377 -0.5400052

Representación de cada variable en un mapa de factores:

if (!empty_nodes) {
  par(mfrow=c(1,1))
  plot(cor[1,], cor[2,], xlim=c(-1,1), ylim=c(-1,1), type="n")
  lines(c(-1,1),c(0,0))
  lines(c(0,0),c(-1,1))
  text(cor[1,], cor[2,], labels=model_colnames, cex=0.75)
  symbols(0,0,circles=1,inches=F,add=T)
}

Importancia de cada variable - varianza ponderada por el tamaño de la celda:

if (!empty_nodes) {
  sigma2 <- sqrt(apply(getCodes(model,1),2,function(x,effectif)
     {m<-sum(effectif*(x-weighted.mean(x,effectif))^2)/(sum(effectif)-1)},
     effectif=nb))
  print(sort(sigma2,decreasing=T))
}

 longitud   latitud   altitud    precip 
0.9753835 0.9659788 0.9582501 0.9242251 

Clustering

if (!empty_nodes) {
  hac <- mpr.hac(model, nb)
}

Visualización de 3 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=3)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=3)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax            tmin            precip           nevada 
 Min.   : 1.000   Min.   : -8.0   Min.   :-58.00   Min.   : 40.00   Min.   :0  
 1st Qu.: 3.000   1st Qu.:135.0   1st Qu.: 63.00   1st Qu.: 54.00   1st Qu.:0  
 Median : 9.000   Median :163.0   Median : 87.00   Median : 63.00   Median :0  
 Mean   : 7.175   Mean   :168.7   Mean   : 91.21   Mean   : 71.42   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:197.5   3rd Qu.:117.00   3rd Qu.: 80.00   3rd Qu.:0  
 Max.   :12.000   Max.   :352.0   Max.   :223.00   Max.   :422.00   Max.   :0  
   prof_nieve         longitud        latitud            altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:39.56   1st Qu.: -6.6000   1st Qu.:  27.1  
 Median :  0.000   Median :42.24   Median : -3.8189   Median :  91.1  
 Mean   :  0.214   Mean   :41.10   Mean   : -3.5750   Mean   : 184.6  
 3rd Qu.:  0.000   3rd Qu.:43.31   3rd Qu.:  0.3664   3rd Qu.: 261.0  
 Max.   :607.000   Max.   :43.57   Max.   :  4.2156   Max.   :2400.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax            tmin             precip      
 Min.   : 1.000   Min.   :-53.0   Min.   :-121.00   Min.   :  0.00  
 1st Qu.: 4.000   1st Qu.:148.0   1st Qu.:  49.00   1st Qu.:  3.00  
 Median : 6.000   Median :197.0   Median :  94.00   Median : 10.00  
 Mean   : 6.453   Mean   :200.8   Mean   :  95.07   Mean   : 13.47  
 3rd Qu.: 9.000   3rd Qu.:258.0   3rd Qu.: 143.00   3rd Qu.: 20.00  
 Max.   :12.000   Max.   :403.0   Max.   : 254.00   Max.   :130.00  
     nevada           prof_nieve           longitud        latitud       
 Min.   :0.000000   Min.   :   0.0000   Min.   :35.28   Min.   :-8.6494  
 1st Qu.:0.000000   1st Qu.:   0.0000   1st Qu.:38.99   1st Qu.:-4.8458  
 Median :0.000000   Median :   0.0000   Median :40.95   Median :-2.4831  
 Mean   :0.000339   Mean   :   0.5194   Mean   :40.51   Mean   :-2.3826  
 3rd Qu.:0.000000   3rd Qu.:   0.0000   3rd Qu.:42.08   3rd Qu.: 0.4942  
 Max.   :6.000000   Max.   :1834.0000   Max.   :43.57   Max.   : 4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  44.0  
 Median : 263.0  
 Mean   : 425.3  
 3rd Qu.: 674.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt           tmax            tmin           precip            nevada 
 Min.   : 1.000   Min.   : 13.0   Min.   :-33.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 4.000   1st Qu.:201.0   1st Qu.:132.0   1st Qu.:  0.000   1st Qu.:0  
 Median : 6.000   Median :225.0   Median :160.0   Median :  1.000   Median :0  
 Mean   : 6.498   Mean   :217.5   Mean   :150.7   Mean   :  6.631   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:253.0   3rd Qu.:190.0   3rd Qu.:  8.000   3rd Qu.:0  
 Max.   :12.000   Max.   :356.0   Max.   :244.0   Max.   :114.000   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.: 0.00000   1st Qu.:28.31   1st Qu.:-16.50   1st Qu.:  25.0  
 Median : 0.00000   Median :28.44   Median :-16.33   Median :  35.0  
 Mean   : 0.03099   Mean   :28.36   Mean   :-16.05   Mean   : 519.5  
 3rd Qu.: 0.00000   3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.: 632.0  
 Max.   :46.00000   Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

Visualización de 4 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=4)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=4)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax            tmin           precip           nevada 
 Min.   : 1.000   Min.   : 42.0   Min.   :-42.0   Min.   : 40.00   Min.   :0  
 1st Qu.: 3.000   1st Qu.:137.0   1st Qu.: 63.0   1st Qu.: 53.00   1st Qu.:0  
 Median : 9.000   Median :164.0   Median : 87.0   Median : 63.00   Median :0  
 Mean   : 7.171   Mean   :169.6   Mean   : 91.7   Mean   : 68.65   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:198.0   3rd Qu.:117.0   3rd Qu.: 79.00   3rd Qu.:0  
 Max.   :12.000   Max.   :352.0   Max.   :219.0   Max.   :150.00   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:39.49   1st Qu.: -6.3500   1st Qu.:  27.1  
 Median : 0.00000   Median :42.24   Median : -3.8189   Median :  91.0  
 Mean   : 0.05583   Mean   :41.12   Mean   : -3.4968   Mean   : 174.5  
 3rd Qu.: 0.00000   3rd Qu.:43.31   3rd Qu.:  0.3664   3rd Qu.: 261.0  
 Max.   :35.00000   Max.   :43.57   Max.   :  4.2156   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax            tmin             precip      
 Min.   : 1.000   Min.   :-53.0   Min.   :-121.00   Min.   :  0.00  
 1st Qu.: 4.000   1st Qu.:148.0   1st Qu.:  49.00   1st Qu.:  3.00  
 Median : 6.000   Median :197.0   Median :  94.00   Median : 10.00  
 Mean   : 6.453   Mean   :200.8   Mean   :  95.07   Mean   : 13.47  
 3rd Qu.: 9.000   3rd Qu.:258.0   3rd Qu.: 143.00   3rd Qu.: 20.00  
 Max.   :12.000   Max.   :403.0   Max.   : 254.00   Max.   :130.00  
     nevada           prof_nieve           longitud        latitud       
 Min.   :0.000000   Min.   :   0.0000   Min.   :35.28   Min.   :-8.6494  
 1st Qu.:0.000000   1st Qu.:   0.0000   1st Qu.:38.99   1st Qu.:-4.8458  
 Median :0.000000   Median :   0.0000   Median :40.95   Median :-2.4831  
 Mean   :0.000339   Mean   :   0.5194   Mean   :40.51   Mean   :-2.3826  
 3rd Qu.:0.000000   3rd Qu.:   0.0000   3rd Qu.:42.08   3rd Qu.: 0.4942  
 Max.   :6.000000   Max.   :1834.0000   Max.   :43.57   Max.   : 4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  44.0  
 Median : 263.0  
 Mean   : 425.3  
 3rd Qu.: 674.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt           tmax            tmin            precip          nevada 
 Min.   : 1.000   Min.   : -8.0   Min.   :-58.00   Min.   :130.0   Min.   :0  
 1st Qu.: 2.000   1st Qu.:107.0   1st Qu.: 45.00   1st Qu.:158.0   1st Qu.:0  
 Median :10.000   Median :129.0   Median : 69.00   Median :173.0   Median :0  
 Mean   : 7.368   Mean   :132.8   Mean   : 70.78   Mean   :187.4   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:151.0   3rd Qu.: 92.00   3rd Qu.:205.0   3rd Qu.:0  
 Max.   :12.000   Max.   :350.0   Max.   :223.00   Max.   :422.0   Max.   :0  
   prof_nieve         longitud        latitud           altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:40.78   1st Qu.: -8.624   1st Qu.: 108.0  
 Median :  0.000   Median :42.24   Median : -8.411   Median : 263.0  
 Mean   :  6.832   Mean   :40.40   Mean   : -6.849   Mean   : 607.2  
 3rd Qu.:  0.000   3rd Qu.:42.89   3rd Qu.: -4.010   3rd Qu.: 609.0  
 Max.   :607.000   Max.   :43.46   Max.   :  2.825   Max.   :2400.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt           tmax            tmin           precip            nevada 
 Min.   : 1.000   Min.   : 13.0   Min.   :-33.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 4.000   1st Qu.:201.0   1st Qu.:132.0   1st Qu.:  0.000   1st Qu.:0  
 Median : 6.000   Median :225.0   Median :160.0   Median :  1.000   Median :0  
 Mean   : 6.498   Mean   :217.5   Mean   :150.7   Mean   :  6.631   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:253.0   3rd Qu.:190.0   3rd Qu.:  8.000   3rd Qu.:0  
 Max.   :12.000   Max.   :356.0   Max.   :244.0   Max.   :114.000   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.: 0.00000   1st Qu.:28.31   1st Qu.:-16.50   1st Qu.:  25.0  
 Median : 0.00000   Median :28.44   Median :-16.33   Median :  35.0  
 Mean   : 0.03099   Mean   :28.36   Mean   :-16.05   Mean   : 519.5  
 3rd Qu.: 0.00000   3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.: 632.0  
 Max.   :46.00000   Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

Visualización de 5 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=5)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=5)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax            tmin           precip           nevada 
 Min.   : 1.000   Min.   : 42.0   Min.   :-42.0   Min.   : 40.00   Min.   :0  
 1st Qu.: 3.000   1st Qu.:137.0   1st Qu.: 63.0   1st Qu.: 53.00   1st Qu.:0  
 Median : 9.000   Median :164.0   Median : 87.0   Median : 63.00   Median :0  
 Mean   : 7.171   Mean   :169.6   Mean   : 91.7   Mean   : 68.65   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:198.0   3rd Qu.:117.0   3rd Qu.: 79.00   3rd Qu.:0  
 Max.   :12.000   Max.   :352.0   Max.   :219.0   Max.   :150.00   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:39.49   1st Qu.: -6.3500   1st Qu.:  27.1  
 Median : 0.00000   Median :42.24   Median : -3.8189   Median :  91.0  
 Mean   : 0.05583   Mean   :41.12   Mean   : -3.4968   Mean   : 174.5  
 3rd Qu.: 0.00000   3rd Qu.:43.31   3rd Qu.:  0.3664   3rd Qu.: 261.0  
 Max.   :35.00000   Max.   :43.57   Max.   :  4.2156   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin             precip     
 Min.   : 1.00   Min.   : -4.0   Min.   :-110.00   Min.   : 0.00  
 1st Qu.: 4.00   1st Qu.:152.0   1st Qu.:  52.00   1st Qu.: 3.00  
 Median : 6.00   Median :200.0   Median :  96.00   Median :10.00  
 Mean   : 6.45   Mean   :204.9   Mean   :  97.89   Mean   :12.75  
 3rd Qu.: 9.00   3rd Qu.:261.0   3rd Qu.: 145.00   3rd Qu.:19.00  
 Max.   :12.00   Max.   :403.0   Max.   : 254.00   Max.   :64.00  
     nevada           prof_nieve          longitud        latitud       
 Min.   :0.000000   Min.   : 0.00000   Min.   :35.28   Min.   :-8.6494  
 1st Qu.:0.000000   1st Qu.: 0.00000   1st Qu.:38.95   1st Qu.:-4.8500  
 Median :0.000000   Median : 0.00000   Median :40.95   Median :-2.6544  
 Mean   :0.000351   Mean   : 0.04854   Mean   :40.45   Mean   :-2.4583  
 3rd Qu.:0.000000   3rd Qu.: 0.00000   3rd Qu.:42.01   3rd Qu.: 0.4914  
 Max.   :6.000000   Max.   :75.00000   Max.   :43.57   Max.   : 4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  44.0  
 Median : 251.0  
 Mean   : 364.9  
 3rd Qu.: 656.0  
 Max.   :1572.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt           tmax             tmin             precip      
 Min.   : 1.000   Min.   :-53.00   Min.   :-121.00   Min.   :  0.00  
 1st Qu.: 4.000   1st Qu.: 31.00   1st Qu.: -30.00   1st Qu.: 16.00  
 Median : 7.000   Median : 78.00   Median :  12.00   Median : 29.00  
 Mean   : 6.535   Mean   : 87.28   Mean   :  16.65   Mean   : 33.58  
 3rd Qu.:10.000   3rd Qu.:140.00   3rd Qu.:  64.00   3rd Qu.: 46.00  
 Max.   :12.000   Max.   :263.00   Max.   : 163.00   Max.   :130.00  
     nevada    prof_nieve        longitud        latitud           altitud    
 Min.   :0   Min.   :   0.0   Min.   :40.78   Min.   :-4.0103   Min.   :1167  
 1st Qu.:0   1st Qu.:   0.0   1st Qu.:40.78   1st Qu.:-4.0103   1st Qu.:1894  
 Median :0   Median :   0.0   Median :42.29   Median : 0.8842   Median :2143  
 Mean   :0   Mean   :  13.6   Mean   :41.93   Mean   :-0.2782   Mean   :2106  
 3rd Qu.:0   3rd Qu.:   0.0   3rd Qu.:42.53   3rd Qu.: 1.5242   3rd Qu.:2316  
 Max.   :0   Max.   :1834.0   Max.   :42.77   Max.   : 2.4378   Max.   :2535  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt           tmax            tmin            precip          nevada 
 Min.   : 1.000   Min.   : -8.0   Min.   :-58.00   Min.   :130.0   Min.   :0  
 1st Qu.: 2.000   1st Qu.:107.0   1st Qu.: 45.00   1st Qu.:158.0   1st Qu.:0  
 Median :10.000   Median :129.0   Median : 69.00   Median :173.0   Median :0  
 Mean   : 7.368   Mean   :132.8   Mean   : 70.78   Mean   :187.4   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:151.0   3rd Qu.: 92.00   3rd Qu.:205.0   3rd Qu.:0  
 Max.   :12.000   Max.   :350.0   Max.   :223.00   Max.   :422.0   Max.   :0  
   prof_nieve         longitud        latitud           altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:40.78   1st Qu.: -8.624   1st Qu.: 108.0  
 Median :  0.000   Median :42.24   Median : -8.411   Median : 263.0  
 Mean   :  6.832   Mean   :40.40   Mean   : -6.849   Mean   : 607.2  
 3rd Qu.:  0.000   3rd Qu.:42.89   3rd Qu.: -4.010   3rd Qu.: 609.0  
 Max.   :607.000   Max.   :43.46   Max.   :  2.825   Max.   :2400.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt           tmax            tmin           precip            nevada 
 Min.   : 1.000   Min.   : 13.0   Min.   :-33.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 4.000   1st Qu.:201.0   1st Qu.:132.0   1st Qu.:  0.000   1st Qu.:0  
 Median : 6.000   Median :225.0   Median :160.0   Median :  1.000   Median :0  
 Mean   : 6.498   Mean   :217.5   Mean   :150.7   Mean   :  6.631   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:253.0   3rd Qu.:190.0   3rd Qu.:  8.000   3rd Qu.:0  
 Max.   :12.000   Max.   :356.0   Max.   :244.0   Max.   :114.000   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.89   Min.   :  14.0  
 1st Qu.: 0.00000   1st Qu.:28.31   1st Qu.:-16.50   1st Qu.:  25.0  
 Median : 0.00000   Median :28.44   Median :-16.33   Median :  35.0  
 Mean   : 0.03099   Mean   :28.36   Mean   :-16.05   Mean   : 519.5  
 3rd Qu.: 0.00000   3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.: 632.0  
 Max.   :46.00000   Max.   :28.95   Max.   :-13.60   Max.   :2371.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

Visualización de 6 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=6)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=6)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax            tmin           precip           nevada 
 Min.   : 1.000   Min.   : 42.0   Min.   :-42.0   Min.   : 40.00   Min.   :0  
 1st Qu.: 3.000   1st Qu.:137.0   1st Qu.: 63.0   1st Qu.: 53.00   1st Qu.:0  
 Median : 9.000   Median :164.0   Median : 87.0   Median : 63.00   Median :0  
 Mean   : 7.171   Mean   :169.6   Mean   : 91.7   Mean   : 68.65   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:198.0   3rd Qu.:117.0   3rd Qu.: 79.00   3rd Qu.:0  
 Max.   :12.000   Max.   :352.0   Max.   :219.0   Max.   :150.00   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:39.49   1st Qu.: -6.3500   1st Qu.:  27.1  
 Median : 0.00000   Median :42.24   Median : -3.8189   Median :  91.0  
 Mean   : 0.05583   Mean   :41.12   Mean   : -3.4968   Mean   : 174.5  
 3rd Qu.: 0.00000   3rd Qu.:43.31   3rd Qu.:  0.3664   3rd Qu.: 261.0  
 Max.   :35.00000   Max.   :43.57   Max.   :  4.2156   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin             precip     
 Min.   : 1.00   Min.   : -4.0   Min.   :-110.00   Min.   : 0.00  
 1st Qu.: 4.00   1st Qu.:152.0   1st Qu.:  52.00   1st Qu.: 3.00  
 Median : 6.00   Median :200.0   Median :  96.00   Median :10.00  
 Mean   : 6.45   Mean   :204.9   Mean   :  97.89   Mean   :12.75  
 3rd Qu.: 9.00   3rd Qu.:261.0   3rd Qu.: 145.00   3rd Qu.:19.00  
 Max.   :12.00   Max.   :403.0   Max.   : 254.00   Max.   :64.00  
     nevada           prof_nieve          longitud        latitud       
 Min.   :0.000000   Min.   : 0.00000   Min.   :35.28   Min.   :-8.6494  
 1st Qu.:0.000000   1st Qu.: 0.00000   1st Qu.:38.95   1st Qu.:-4.8500  
 Median :0.000000   Median : 0.00000   Median :40.95   Median :-2.6544  
 Mean   :0.000351   Mean   : 0.04854   Mean   :40.45   Mean   :-2.4583  
 3rd Qu.:0.000000   3rd Qu.: 0.00000   3rd Qu.:42.01   3rd Qu.: 0.4914  
 Max.   :6.000000   Max.   :75.00000   Max.   :43.57   Max.   : 4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  44.0  
 Median : 251.0  
 Mean   : 364.9  
 3rd Qu.: 656.0  
 Max.   :1572.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt           tmax             tmin             precip      
 Min.   : 1.000   Min.   :-53.00   Min.   :-121.00   Min.   :  0.00  
 1st Qu.: 4.000   1st Qu.: 31.00   1st Qu.: -30.00   1st Qu.: 16.00  
 Median : 7.000   Median : 78.00   Median :  12.00   Median : 29.00  
 Mean   : 6.535   Mean   : 87.28   Mean   :  16.65   Mean   : 33.58  
 3rd Qu.:10.000   3rd Qu.:140.00   3rd Qu.:  64.00   3rd Qu.: 46.00  
 Max.   :12.000   Max.   :263.00   Max.   : 163.00   Max.   :130.00  
     nevada    prof_nieve        longitud        latitud           altitud    
 Min.   :0   Min.   :   0.0   Min.   :40.78   Min.   :-4.0103   Min.   :1167  
 1st Qu.:0   1st Qu.:   0.0   1st Qu.:40.78   1st Qu.:-4.0103   1st Qu.:1894  
 Median :0   Median :   0.0   Median :42.29   Median : 0.8842   Median :2143  
 Mean   :0   Mean   :  13.6   Mean   :41.93   Mean   :-0.2782   Mean   :2106  
 3rd Qu.:0   3rd Qu.:   0.0   3rd Qu.:42.53   3rd Qu.: 1.5242   3rd Qu.:2316  
 Max.   :0   Max.   :1834.0   Max.   :42.77   Max.   : 2.4378   Max.   :2535  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt           tmax            tmin            precip          nevada 
 Min.   : 1.000   Min.   : -8.0   Min.   :-58.00   Min.   :130.0   Min.   :0  
 1st Qu.: 2.000   1st Qu.:107.0   1st Qu.: 45.00   1st Qu.:158.0   1st Qu.:0  
 Median :10.000   Median :129.0   Median : 69.00   Median :173.0   Median :0  
 Mean   : 7.368   Mean   :132.8   Mean   : 70.78   Mean   :187.4   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:151.0   3rd Qu.: 92.00   3rd Qu.:205.0   3rd Qu.:0  
 Max.   :12.000   Max.   :350.0   Max.   :223.00   Max.   :422.0   Max.   :0  
   prof_nieve         longitud        latitud           altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:40.78   1st Qu.: -8.624   1st Qu.: 108.0  
 Median :  0.000   Median :42.24   Median : -8.411   Median : 263.0  
 Mean   :  6.832   Mean   :40.40   Mean   : -6.849   Mean   : 607.2  
 3rd Qu.:  0.000   3rd Qu.:42.89   3rd Qu.: -4.010   3rd Qu.: 609.0  
 Max.   :607.000   Max.   :43.46   Max.   :  2.825   Max.   :2400.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt           tmax            tmin            precip           nevada 
 Min.   : 1.000   Min.   : 13.0   Min.   :-33.00   Min.   :  0.00   Min.   :0  
 1st Qu.: 4.000   1st Qu.: 94.0   1st Qu.: 23.00   1st Qu.:  0.00   1st Qu.:0  
 Median : 7.000   Median :129.0   Median : 51.00   Median :  3.00   Median :0  
 Mean   : 6.585   Mean   :138.4   Mean   : 60.83   Mean   : 10.29   Mean   :0  
 3rd Qu.:10.000   3rd Qu.:183.0   3rd Qu.: 98.00   3rd Qu.: 13.00   3rd Qu.:0  
 Max.   :12.000   Max.   :253.0   Max.   :159.00   Max.   :114.00   Max.   :0  
   prof_nieve         longitud        latitud         altitud    
 Min.   : 0.0000   Min.   :28.31   Min.   :-16.5   Min.   :2371  
 1st Qu.: 0.0000   1st Qu.:28.31   1st Qu.:-16.5   1st Qu.:2371  
 Median : 0.0000   Median :28.31   Median :-16.5   Median :2371  
 Mean   : 0.1766   Mean   :28.31   Mean   :-16.5   Mean   :2371  
 3rd Qu.: 0.0000   3rd Qu.:28.31   3rd Qu.:-16.5   3rd Qu.:2371  
 Max.   :46.0000   Max.   :28.31   Max.   :-16.5   Max.   :2371  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt           tmax            tmin           precip          nevada 
 Min.   : 1.000   Min.   : 87.0   Min.   : 64.0   Min.   : 0.00   Min.   :0  
 1st Qu.: 3.000   1st Qu.:212.0   1st Qu.:150.0   1st Qu.: 0.00   1st Qu.:0  
 Median : 6.000   Median :233.0   Median :168.5   Median : 1.00   Median :0  
 Mean   : 6.479   Mean   :234.1   Mean   :169.6   Mean   : 5.86   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:259.0   3rd Qu.:196.0   3rd Qu.: 7.00   3rd Qu.:0  
 Max.   :12.000   Max.   :356.0   Max.   :244.0   Max.   :73.00   Max.   :0  
   prof_nieve           longitud        latitud          altitud   
 Min.   :0.0000000   Min.   :27.82   Min.   :-17.89   Min.   : 14  
 1st Qu.:0.0000000   1st Qu.:28.05   1st Qu.:-16.56   1st Qu.: 25  
 Median :0.0000000   Median :28.46   Median :-16.26   Median : 33  
 Mean   :0.0003539   Mean   :28.38   Mean   :-15.95   Mean   :130  
 3rd Qu.:0.0000000   3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.: 64  
 Max.   :2.0000000   Max.   :28.95   Max.   :-13.60   Max.   :632  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

Visualización de 8 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=8)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=8)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)
  df.cluster07 <- subset(df, cluster==7)
  df.cluster08 <- subset(df, cluster==8)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster07 <- select(df.cluster07, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster08 <- select(df.cluster08, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax            tmin           precip           nevada 
 Min.   : 1.000   Min.   : 42.0   Min.   :-42.0   Min.   : 40.00   Min.   :0  
 1st Qu.: 3.000   1st Qu.:137.0   1st Qu.: 63.0   1st Qu.: 53.00   1st Qu.:0  
 Median : 9.000   Median :164.0   Median : 87.0   Median : 63.00   Median :0  
 Mean   : 7.171   Mean   :169.6   Mean   : 91.7   Mean   : 68.65   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:198.0   3rd Qu.:117.0   3rd Qu.: 79.00   3rd Qu.:0  
 Max.   :12.000   Max.   :352.0   Max.   :219.0   Max.   :150.00   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:39.49   1st Qu.: -6.3500   1st Qu.:  27.1  
 Median : 0.00000   Median :42.24   Median : -3.8189   Median :  91.0  
 Mean   : 0.05583   Mean   :41.12   Mean   : -3.4968   Mean   : 174.5  
 3rd Qu.: 0.00000   3rd Qu.:43.31   3rd Qu.:  0.3664   3rd Qu.: 261.0  
 Max.   :35.00000   Max.   :43.57   Max.   :  4.2156   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax            tmin            precip          nevada 
 Min.   : 1.000   Min.   :  7.0   Min.   :-62.00   Min.   : 0.00   Min.   :0  
 1st Qu.: 4.000   1st Qu.:143.0   1st Qu.: 65.00   1st Qu.:15.00   1st Qu.:0  
 Median : 6.000   Median :179.0   Median : 96.00   Median :27.00   Median :0  
 Mean   : 6.416   Mean   :180.4   Mean   : 96.59   Mean   :26.37   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:218.0   3rd Qu.:132.00   3rd Qu.:37.00   3rd Qu.:0  
 Max.   :12.000   Max.   :340.0   Max.   :193.00   Max.   :54.00   Max.   :0  
   prof_nieve          longitud        latitud           altitud     
 Min.   : 0.00000   Min.   :39.47   Min.   :-8.6494   Min.   :  4.0  
 1st Qu.: 0.00000   1st Qu.:42.85   1st Qu.:-8.4106   1st Qu.: 52.0  
 Median : 0.00000   Median :43.31   Median :-6.0442   Median :108.0  
 Mean   : 0.06027   Mean   :43.11   Mean   :-5.9040   Mean   :179.4  
 3rd Qu.: 0.00000   3rd Qu.:43.43   3rd Qu.:-3.8189   3rd Qu.:336.0  
 Max.   :40.00000   Max.   :43.57   Max.   : 0.4483   Max.   :534.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt           tmax            tmin            precip     
 Min.   : 1.000   Min.   : -4.0   Min.   :-110.0   Min.   : 0.00  
 1st Qu.: 4.000   1st Qu.:123.0   1st Qu.:  23.0   1st Qu.: 3.00  
 Median : 6.000   Median :183.0   Median :  65.0   Median : 9.00  
 Mean   : 6.481   Mean   :192.1   Mean   :  71.3   Mean   :12.15  
 3rd Qu.: 9.000   3rd Qu.:261.0   3rd Qu.: 118.0   3rd Qu.:18.00  
 Max.   :12.000   Max.   :400.0   Max.   : 250.0   Max.   :64.00  
     nevada           prof_nieve          longitud        latitud      
 Min.   :0.000000   Min.   : 0.00000   Min.   :37.13   Min.   :-6.600  
 1st Qu.:0.000000   1st Qu.: 0.00000   1st Qu.:40.07   1st Qu.:-4.680  
 Median :0.000000   Median : 0.00000   Median :40.70   Median :-3.764  
 Mean   :0.000504   Mean   : 0.08502   Mean   :40.65   Mean   :-3.367  
 3rd Qu.:0.000000   3rd Qu.: 0.00000   3rd Qu.:41.65   3rd Qu.:-2.138  
 Max.   :6.000000   Max.   :75.00000   Max.   :42.70   Max.   : 2.418  
    altitud    
 Min.   : 405  
 1st Qu.: 627  
 Median : 735  
 Mean   : 770  
 3rd Qu.: 916  
 Max.   :1572  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt           tmax             tmin             precip      
 Min.   : 1.000   Min.   :-53.00   Min.   :-121.00   Min.   :  0.00  
 1st Qu.: 4.000   1st Qu.: 31.00   1st Qu.: -30.00   1st Qu.: 16.00  
 Median : 7.000   Median : 78.00   Median :  12.00   Median : 29.00  
 Mean   : 6.535   Mean   : 87.28   Mean   :  16.65   Mean   : 33.58  
 3rd Qu.:10.000   3rd Qu.:140.00   3rd Qu.:  64.00   3rd Qu.: 46.00  
 Max.   :12.000   Max.   :263.00   Max.   : 163.00   Max.   :130.00  
     nevada    prof_nieve        longitud        latitud           altitud    
 Min.   :0   Min.   :   0.0   Min.   :40.78   Min.   :-4.0103   Min.   :1167  
 1st Qu.:0   1st Qu.:   0.0   1st Qu.:40.78   1st Qu.:-4.0103   1st Qu.:1894  
 Median :0   Median :   0.0   Median :42.29   Median : 0.8842   Median :2143  
 Mean   :0   Mean   :  13.6   Mean   :41.93   Mean   :-0.2782   Mean   :2106  
 3rd Qu.:0   3rd Qu.:   0.0   3rd Qu.:42.53   3rd Qu.: 1.5242   3rd Qu.:2316  
 Max.   :0   Max.   :1834.0   Max.   :42.77   Max.   : 2.4378   Max.   :2535  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt           tmax            tmin            precip          nevada 
 Min.   : 1.000   Min.   : -8.0   Min.   :-58.00   Min.   :130.0   Min.   :0  
 1st Qu.: 2.000   1st Qu.:107.0   1st Qu.: 45.00   1st Qu.:158.0   1st Qu.:0  
 Median :10.000   Median :129.0   Median : 69.00   Median :173.0   Median :0  
 Mean   : 7.368   Mean   :132.8   Mean   : 70.78   Mean   :187.4   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:151.0   3rd Qu.: 92.00   3rd Qu.:205.0   3rd Qu.:0  
 Max.   :12.000   Max.   :350.0   Max.   :223.00   Max.   :422.0   Max.   :0  
   prof_nieve         longitud        latitud           altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:40.78   1st Qu.: -8.624   1st Qu.: 108.0  
 Median :  0.000   Median :42.24   Median : -8.411   Median : 263.0  
 Mean   :  6.832   Mean   :40.40   Mean   : -6.849   Mean   : 607.2  
 3rd Qu.:  0.000   3rd Qu.:42.89   3rd Qu.: -4.010   3rd Qu.: 609.0  
 Max.   :607.000   Max.   :43.46   Max.   :  2.825   Max.   :2400.0  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt           tmax            tmin           precip     
 Min.   : 1.000   Min.   :  8.0   Min.   :-68.0   Min.   : 0.00  
 1st Qu.: 4.000   1st Qu.:169.0   1st Qu.: 70.0   1st Qu.: 2.00  
 Median : 6.000   Median :215.0   Median :115.0   Median : 7.00  
 Mean   : 6.437   Mean   :218.9   Mean   :115.6   Mean   :10.01  
 3rd Qu.: 9.000   3rd Qu.:271.0   3rd Qu.:164.0   3rd Qu.:16.00  
 Max.   :12.000   Max.   :403.0   Max.   :254.0   Max.   :43.00  
     nevada           prof_nieve          longitud        latitud       
 Min.   :0.000000   Min.   : 0.00000   Min.   :35.28   Min.   :-6.9492  
 1st Qu.:0.000000   1st Qu.: 0.00000   1st Qu.:37.79   1st Qu.:-3.7994  
 Median :0.000000   Median : 0.00000   Median :39.95   Median : 0.3264  
 Mean   :0.000331   Mean   : 0.02189   Mean   :39.71   Mean   :-1.0685  
 3rd Qu.:0.000000   3rd Qu.: 0.00000   3rd Qu.:41.65   3rd Qu.: 1.1789  
 Max.   :4.000000   Max.   :59.00000   Max.   :43.49   Max.   : 4.2156  
    altitud     
 Min.   :  1.0  
 1st Qu.: 21.0  
 Median : 69.0  
 Mean   :141.6  
 3rd Qu.:192.0  
 Max.   :953.0  

if (!empty_nodes) summary(df.cluster07)

   fecha_cnt           tmax            tmin            precip           nevada 
 Min.   : 1.000   Min.   : 13.0   Min.   :-33.00   Min.   :  0.00   Min.   :0  
 1st Qu.: 4.000   1st Qu.: 94.0   1st Qu.: 23.00   1st Qu.:  0.00   1st Qu.:0  
 Median : 7.000   Median :129.0   Median : 51.00   Median :  3.00   Median :0  
 Mean   : 6.585   Mean   :138.4   Mean   : 60.83   Mean   : 10.29   Mean   :0  
 3rd Qu.:10.000   3rd Qu.:183.0   3rd Qu.: 98.00   3rd Qu.: 13.00   3rd Qu.:0  
 Max.   :12.000   Max.   :253.0   Max.   :159.00   Max.   :114.00   Max.   :0  
   prof_nieve         longitud        latitud         altitud    
 Min.   : 0.0000   Min.   :28.31   Min.   :-16.5   Min.   :2371  
 1st Qu.: 0.0000   1st Qu.:28.31   1st Qu.:-16.5   1st Qu.:2371  
 Median : 0.0000   Median :28.31   Median :-16.5   Median :2371  
 Mean   : 0.1766   Mean   :28.31   Mean   :-16.5   Mean   :2371  
 3rd Qu.: 0.0000   3rd Qu.:28.31   3rd Qu.:-16.5   3rd Qu.:2371  
 Max.   :46.0000   Max.   :28.31   Max.   :-16.5   Max.   :2371  

if (!empty_nodes) summary(df.cluster08)

   fecha_cnt           tmax            tmin           precip          nevada 
 Min.   : 1.000   Min.   : 87.0   Min.   : 64.0   Min.   : 0.00   Min.   :0  
 1st Qu.: 3.000   1st Qu.:212.0   1st Qu.:150.0   1st Qu.: 0.00   1st Qu.:0  
 Median : 6.000   Median :233.0   Median :168.5   Median : 1.00   Median :0  
 Mean   : 6.479   Mean   :234.1   Mean   :169.6   Mean   : 5.86   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:259.0   3rd Qu.:196.0   3rd Qu.: 7.00   3rd Qu.:0  
 Max.   :12.000   Max.   :356.0   Max.   :244.0   Max.   :73.00   Max.   :0  
   prof_nieve           longitud        latitud          altitud   
 Min.   :0.0000000   Min.   :27.82   Min.   :-17.89   Min.   : 14  
 1st Qu.:0.0000000   1st Qu.:28.05   1st Qu.:-16.56   1st Qu.: 25  
 Median :0.0000000   Median :28.46   Median :-16.26   Median : 33  
 Mean   :0.0003539   Mean   :28.38   Mean   :-15.95   Mean   :130  
 3rd Qu.:0.0000000   3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.: 64  
 Max.   :2.0000000   Max.   :28.95   Max.   :-13.60   Max.   :632  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1], dim(df.cluster07)[1], dim(df.cluster08)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06", "cluster07", "cluster08"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.hist(df.cluster07)

if (!empty_nodes) mpr.hist(df.cluster08)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster07)

if (!empty_nodes) mpr.boxplot(df.cluster08)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
  df.cluster07.grouped <- mpr.group_by_geo(df.cluster07)
  df.cluster08.grouped <- mpr.group_by_geo(df.cluster08)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster07.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster08.grouped)

Visualización de 10 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=10)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=10)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)
  df.cluster07 <- subset(df, cluster==7)
  df.cluster08 <- subset(df, cluster==8)
  df.cluster09 <- subset(df, cluster==9)
  df.cluster10 <- subset(df, cluster==10)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster07 <- select(df.cluster07, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster08 <- select(df.cluster08, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster09 <- select(df.cluster09, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster10 <- select(df.cluster10, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax            tmin            precip          nevada 
 Min.   : 1.000   Min.   : 51.0   Min.   :-22.00   Min.   : 86.0   Min.   :0  
 1st Qu.: 3.000   1st Qu.:127.0   1st Qu.: 62.00   1st Qu.: 97.0   1st Qu.:0  
 Median :10.000   Median :150.0   Median : 83.00   Median :106.0   Median :0  
 Mean   : 7.455   Mean   :156.8   Mean   : 86.71   Mean   :110.1   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:179.0   3rd Qu.:109.00   3rd Qu.:120.0   3rd Qu.:0  
 Max.   :12.000   Max.   :326.0   Max.   :211.00   Max.   :150.0   Max.   :0  
   prof_nieve         longitud        latitud           altitud      
 Min.   :0.00000   Min.   :27.92   Min.   :-16.329   Min.   :   1.0  
 1st Qu.:0.00000   1st Qu.:41.42   1st Qu.: -8.411   1st Qu.:  22.0  
 Median :0.00000   Median :42.44   Median : -5.600   Median : 108.0  
 Mean   :0.09566   Mean   :41.66   Mean   : -4.919   Mean   : 186.4  
 3rd Qu.:0.00000   3rd Qu.:43.31   3rd Qu.: -2.039   3rd Qu.: 261.0  
 Max.   :6.00000   Max.   :43.57   Max.   :  3.035   Max.   :1894.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax            tmin            precip          nevada 
 Min.   : 1.000   Min.   :  7.0   Min.   :-62.00   Min.   : 0.00   Min.   :0  
 1st Qu.: 4.000   1st Qu.:143.0   1st Qu.: 65.00   1st Qu.:15.00   1st Qu.:0  
 Median : 6.000   Median :179.0   Median : 96.00   Median :27.00   Median :0  
 Mean   : 6.416   Mean   :180.4   Mean   : 96.59   Mean   :26.37   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:218.0   3rd Qu.:132.00   3rd Qu.:37.00   3rd Qu.:0  
 Max.   :12.000   Max.   :340.0   Max.   :193.00   Max.   :54.00   Max.   :0  
   prof_nieve          longitud        latitud           altitud     
 Min.   : 0.00000   Min.   :39.47   Min.   :-8.6494   Min.   :  4.0  
 1st Qu.: 0.00000   1st Qu.:42.85   1st Qu.:-8.4106   1st Qu.: 52.0  
 Median : 0.00000   Median :43.31   Median :-6.0442   Median :108.0  
 Mean   : 0.06027   Mean   :43.11   Mean   :-5.9040   Mean   :179.4  
 3rd Qu.: 0.00000   3rd Qu.:43.43   3rd Qu.:-3.8189   3rd Qu.:336.0  
 Max.   :40.00000   Max.   :43.57   Max.   : 0.4483   Max.   :534.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt           tmax            tmin            precip     
 Min.   : 1.000   Min.   : -4.0   Min.   :-110.0   Min.   : 0.00  
 1st Qu.: 4.000   1st Qu.:123.0   1st Qu.:  23.0   1st Qu.: 3.00  
 Median : 6.000   Median :183.0   Median :  65.0   Median : 9.00  
 Mean   : 6.481   Mean   :192.1   Mean   :  71.3   Mean   :12.15  
 3rd Qu.: 9.000   3rd Qu.:261.0   3rd Qu.: 118.0   3rd Qu.:18.00  
 Max.   :12.000   Max.   :400.0   Max.   : 250.0   Max.   :64.00  
     nevada           prof_nieve          longitud        latitud      
 Min.   :0.000000   Min.   : 0.00000   Min.   :37.13   Min.   :-6.600  
 1st Qu.:0.000000   1st Qu.: 0.00000   1st Qu.:40.07   1st Qu.:-4.680  
 Median :0.000000   Median : 0.00000   Median :40.70   Median :-3.764  
 Mean   :0.000504   Mean   : 0.08502   Mean   :40.65   Mean   :-3.367  
 3rd Qu.:0.000000   3rd Qu.: 0.00000   3rd Qu.:41.65   3rd Qu.:-2.138  
 Max.   :6.000000   Max.   :75.00000   Max.   :42.70   Max.   : 2.418  
    altitud    
 Min.   : 405  
 1st Qu.: 627  
 Median : 735  
 Mean   : 770  
 3rd Qu.: 916  
 Max.   :1572  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt           tmax             tmin             precip      
 Min.   : 1.000   Min.   :-53.00   Min.   :-121.00   Min.   :  0.00  
 1st Qu.: 4.000   1st Qu.: 31.00   1st Qu.: -30.00   1st Qu.: 16.00  
 Median : 7.000   Median : 78.00   Median :  12.00   Median : 29.00  
 Mean   : 6.535   Mean   : 87.28   Mean   :  16.65   Mean   : 33.58  
 3rd Qu.:10.000   3rd Qu.:140.00   3rd Qu.:  64.00   3rd Qu.: 46.00  
 Max.   :12.000   Max.   :263.00   Max.   : 163.00   Max.   :130.00  
     nevada    prof_nieve        longitud        latitud           altitud    
 Min.   :0   Min.   :   0.0   Min.   :40.78   Min.   :-4.0103   Min.   :1167  
 1st Qu.:0   1st Qu.:   0.0   1st Qu.:40.78   1st Qu.:-4.0103   1st Qu.:1894  
 Median :0   Median :   0.0   Median :42.29   Median : 0.8842   Median :2143  
 Mean   :0   Mean   :  13.6   Mean   :41.93   Mean   :-0.2782   Mean   :2106  
 3rd Qu.:0   3rd Qu.:   0.0   3rd Qu.:42.53   3rd Qu.: 1.5242   3rd Qu.:2316  
 Max.   :0   Max.   :1834.0   Max.   :42.77   Max.   : 2.4378   Max.   :2535  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt           tmax            tmin            precip          nevada 
 Min.   : 1.000   Min.   : -8.0   Min.   :-58.00   Min.   :130.0   Min.   :0  
 1st Qu.: 2.000   1st Qu.:107.0   1st Qu.: 45.00   1st Qu.:158.0   1st Qu.:0  
 Median :10.000   Median :129.0   Median : 69.00   Median :173.0   Median :0  
 Mean   : 7.368   Mean   :132.8   Mean   : 70.78   Mean   :187.4   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:151.0   3rd Qu.: 92.00   3rd Qu.:205.0   3rd Qu.:0  
 Max.   :12.000   Max.   :350.0   Max.   :223.00   Max.   :422.0   Max.   :0  
   prof_nieve         longitud        latitud           altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:40.78   1st Qu.: -8.624   1st Qu.: 108.0  
 Median :  0.000   Median :42.24   Median : -8.411   Median : 263.0  
 Mean   :  6.832   Mean   :40.40   Mean   : -6.849   Mean   : 607.2  
 3rd Qu.:  0.000   3rd Qu.:42.89   3rd Qu.: -4.010   3rd Qu.: 609.0  
 Max.   :607.000   Max.   :43.46   Max.   :  2.825   Max.   :2400.0  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt           tmax            tmin            precip           nevada 
 Min.   : 1.000   Min.   : 42.0   Min.   :-42.00   Min.   : 40.00   Min.   :0  
 1st Qu.: 3.000   1st Qu.:139.0   1st Qu.: 63.00   1st Qu.: 52.00   1st Qu.:0  
 Median : 9.000   Median :167.0   Median : 89.00   Median : 60.00   Median :0  
 Mean   : 7.121   Mean   :171.8   Mean   : 92.58   Mean   : 61.35   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:200.0   3rd Qu.:119.00   3rd Qu.: 70.00   3rd Qu.:0  
 Max.   :12.000   Max.   :352.0   Max.   :219.00   Max.   :115.00   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:39.48   1st Qu.: -6.0556   1st Qu.:  27.1  
 Median : 0.00000   Median :42.07   Median : -3.7994   Median :  90.0  
 Mean   : 0.04881   Mean   :41.02   Mean   : -3.2460   Mean   : 172.4  
 3rd Qu.: 0.00000   3rd Qu.:43.31   3rd Qu.:  0.4914   3rd Qu.: 261.0  
 Max.   :35.00000   Max.   :43.57   Max.   :  4.2156   Max.   :1082.0  

if (!empty_nodes) summary(df.cluster07)

   fecha_cnt           tmax            tmin           precip     
 Min.   : 1.000   Min.   :  8.0   Min.   :-68.0   Min.   : 0.00  
 1st Qu.: 3.000   1st Qu.:163.0   1st Qu.: 63.0   1st Qu.: 3.00  
 Median : 6.000   Median :209.0   Median :105.0   Median : 8.00  
 Mean   : 6.438   Mean   :213.2   Mean   :109.5   Mean   :10.25  
 3rd Qu.: 9.000   3rd Qu.:268.0   3rd Qu.:159.0   3rd Qu.:15.00  
 Max.   :12.000   Max.   :386.0   Max.   :254.0   Max.   :43.00  
     nevada           prof_nieve          longitud        latitud       
 Min.   :0.000000   Min.   : 0.00000   Min.   :37.79   Min.   :-3.8314  
 1st Qu.:0.000000   1st Qu.: 0.00000   1st Qu.:39.49   1st Qu.:-0.4820  
 Median :0.000000   Median : 0.00000   Median :41.29   Median : 0.5950  
 Mean   :0.000454   Mean   : 0.02493   Mean   :40.77   Mean   : 0.5457  
 3rd Qu.:0.000000   3rd Qu.: 0.00000   3rd Qu.:41.91   3rd Qu.: 1.8081  
 Max.   :4.000000   Max.   :59.00000   Max.   :43.49   Max.   : 4.2156  
    altitud     
 Min.   :  1.0  
 1st Qu.: 32.0  
 Median : 81.0  
 Mean   :173.8  
 3rd Qu.:263.0  
 Max.   :953.0  

if (!empty_nodes) summary(df.cluster08)

   fecha_cnt           tmax            tmin            precip           nevada 
 Min.   : 1.000   Min.   : 13.0   Min.   :-33.00   Min.   :  0.00   Min.   :0  
 1st Qu.: 4.000   1st Qu.: 94.0   1st Qu.: 23.00   1st Qu.:  0.00   1st Qu.:0  
 Median : 7.000   Median :129.0   Median : 51.00   Median :  3.00   Median :0  
 Mean   : 6.585   Mean   :138.4   Mean   : 60.83   Mean   : 10.29   Mean   :0  
 3rd Qu.:10.000   3rd Qu.:183.0   3rd Qu.: 98.00   3rd Qu.: 13.00   3rd Qu.:0  
 Max.   :12.000   Max.   :253.0   Max.   :159.00   Max.   :114.00   Max.   :0  
   prof_nieve         longitud        latitud         altitud    
 Min.   : 0.0000   Min.   :28.31   Min.   :-16.5   Min.   :2371  
 1st Qu.: 0.0000   1st Qu.:28.31   1st Qu.:-16.5   1st Qu.:2371  
 Median : 0.0000   Median :28.31   Median :-16.5   Median :2371  
 Mean   : 0.1766   Mean   :28.31   Mean   :-16.5   Mean   :2371  
 3rd Qu.: 0.0000   3rd Qu.:28.31   3rd Qu.:-16.5   3rd Qu.:2371  
 Max.   :46.0000   Max.   :28.31   Max.   :-16.5   Max.   :2371  

if (!empty_nodes) summary(df.cluster09)

   fecha_cnt           tmax            tmin           precip           nevada 
 Min.   : 1.000   Min.   : 95.0   Min.   :-17.0   Min.   : 0.000   Min.   :0  
 1st Qu.: 4.000   1st Qu.:182.0   1st Qu.: 93.0   1st Qu.: 0.000   1st Qu.:0  
 Median : 6.000   Median :227.0   Median :132.0   Median : 5.000   Median :0  
 Mean   : 6.435   Mean   :234.4   Mean   :132.2   Mean   : 9.355   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:281.0   3rd Qu.:175.0   3rd Qu.:16.000   3rd Qu.:0  
 Max.   :12.000   Max.   :403.0   Max.   :246.0   Max.   :42.000   Max.   :0  
   prof_nieve          longitud        latitud          altitud      
 Min.   : 0.00000   Min.   :35.28   Min.   :-6.949   Min.   :  1.00  
 1st Qu.: 0.00000   1st Qu.:36.50   1st Qu.:-6.332   1st Qu.: 19.00  
 Median : 0.00000   Median :36.83   Median :-5.616   Median : 32.00  
 Mean   : 0.01374   Mean   :36.87   Mean   :-5.393   Mean   : 55.32  
 3rd Qu.: 0.00000   3rd Qu.:37.26   3rd Qu.:-4.846   3rd Qu.: 87.00  
 Max.   :34.00000   Max.   :39.47   Max.   :-2.357   Max.   :405.00  

if (!empty_nodes) summary(df.cluster10)

   fecha_cnt           tmax            tmin           precip          nevada 
 Min.   : 1.000   Min.   : 87.0   Min.   : 64.0   Min.   : 0.00   Min.   :0  
 1st Qu.: 3.000   1st Qu.:212.0   1st Qu.:150.0   1st Qu.: 0.00   1st Qu.:0  
 Median : 6.000   Median :233.0   Median :168.5   Median : 1.00   Median :0  
 Mean   : 6.479   Mean   :234.1   Mean   :169.6   Mean   : 5.86   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:259.0   3rd Qu.:196.0   3rd Qu.: 7.00   3rd Qu.:0  
 Max.   :12.000   Max.   :356.0   Max.   :244.0   Max.   :73.00   Max.   :0  
   prof_nieve           longitud        latitud          altitud   
 Min.   :0.0000000   Min.   :27.82   Min.   :-17.89   Min.   : 14  
 1st Qu.:0.0000000   1st Qu.:28.05   1st Qu.:-16.56   1st Qu.: 25  
 Median :0.0000000   Median :28.46   Median :-16.26   Median : 33  
 Mean   :0.0003539   Mean   :28.38   Mean   :-15.95   Mean   :130  
 3rd Qu.:0.0000000   3rd Qu.:28.48   3rd Qu.:-15.39   3rd Qu.: 64  
 Max.   :2.0000000   Max.   :28.95   Max.   :-13.60   Max.   :632  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1], dim(df.cluster07)[1], dim(df.cluster08)[1], dim(df.cluster09)[1], dim(df.cluster10)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06", "cluster07", "cluster08", "cluster09", "cluster10"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.hist(df.cluster07)

if (!empty_nodes) mpr.hist(df.cluster08)

if (!empty_nodes) mpr.hist(df.cluster09)

if (!empty_nodes) mpr.hist(df.cluster10)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster07)

if (!empty_nodes) mpr.boxplot(df.cluster08)

if (!empty_nodes) mpr.boxplot(df.cluster09)

if (!empty_nodes) mpr.boxplot(df.cluster10)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
  df.cluster07.grouped <- mpr.group_by_geo(df.cluster07)
  df.cluster08.grouped <- mpr.group_by_geo(df.cluster08)
  df.cluster09.grouped <- mpr.group_by_geo(df.cluster09)
  df.cluster10.grouped <- mpr.group_by_geo(df.cluster10)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster07.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster08.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster09.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster10.grouped)